# FAMED-Net: A Fast and Accurate Multi-scale End-to-end Dehazing Network

## TL;DR

FAMED-Net is a lightweight, multi-scale end-to-end neural network designed for fast and accurate image dehazing, outperforming existing models in efficiency and restoration quality.

## Contribution

The paper introduces FAMED-Net, a novel multi-scale dehazing network that is both computationally efficient and highly effective, addressing overcomplexity in prior models.

## Key findings

- Outperforms state-of-the-art models in accuracy and efficiency
- Demonstrates strong generalization on real-world hazy images
- Maintains low model complexity with layer reuse and small kernels

## Abstract

Single image dehazing is a critical image pre-processing step for subsequent high-level computer vision tasks. However, it remains challenging due to its ill-posed nature. Existing dehazing models tend to suffer from model overcomplexity and computational inefficiency or have limited representation capacity. To tackle these challenges, here we propose a fast and accurate multi-scale end-to-end dehazing network called FAMED-Net, which comprises encoders at three scales and a fusion module to efficiently and directly learn the haze-free image. Each encoder consists of cascaded and densely connected point-wise convolutional layers and pooling layers. Since no larger convolutional kernels are used and features are reused layer-by-layer, FAMED-Net is lightweight and computationally efficient. Thorough empirical studies on public synthetic datasets (including RESIDE) and real-world hazy images demonstrate the superiority of FAMED-Net over other representative state-of-the-art models with respect to model complexity, computational efficiency, restoration accuracy, and cross-set generalization. The code will be made publicly available.